Transposition with MPI_put
call mpi_barrier(MPI_COMM_WORLD,ierr)
target_disp=(1+(ktag-1)*len)-1
call mpi_put(x(1,ksnding(kk), len, MPI_REAL8, ipsndto(kk), target_disp, len,
call mpi_win_fence(0, iwin, ierr)
! Cleanup - destroy window
call mpi_barrier(MPI_COMM_WORLD,ierr)
call mpi_win_free(iwin, ierr)